INDEX

Explanations

code structure indicators, such as braces and parentheses

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

StandardCharsets

-0.57

]=="

-0.56

DataAnnotations

-0.56

eron

-0.54

EnableWeb

-0.54

ManagedBean

-0.53

AccessFile

-0.53

runApp

-0.53

JPA

-0.51

 Bohn

-0.50

POSITIVE LOGITS

 AssemblyProduct

0.66

UnusedPrivate

0.54

 propOrder

0.53

 Именно

0.51

adomo

0.51

velocityY

0.51

IsMutable

0.50

 հղումներ

0.50

chtig

0.50

ագրություններ

0.49

Activations Density 0.090%

code structure indicators, such as braces and parentheses

No Comments

No Known Activations